CN113160016A - Scientific research thesis management method and system based on artificial intelligence - Google Patents
Scientific research thesis management method and system based on artificial intelligence Download PDFInfo
- Publication number
- CN113160016A CN113160016A CN202110581579.5A CN202110581579A CN113160016A CN 113160016 A CN113160016 A CN 113160016A CN 202110581579 A CN202110581579 A CN 202110581579A CN 113160016 A CN113160016 A CN 113160016A
- Authority
- CN
- China
- Prior art keywords
- information
- scientific research
- thesis
- module
- management
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000007726 management method Methods 0.000 title claims abstract description 72
- 238000011160 research Methods 0.000 title claims description 106
- 238000013473 artificial intelligence Methods 0.000 title claims description 24
- 230000002452 interceptive effect Effects 0.000 claims abstract description 19
- 238000012795 verification Methods 0.000 claims abstract description 10
- 238000012550 audit Methods 0.000 claims description 17
- 102100032202 Cornulin Human genes 0.000 claims description 12
- 101000920981 Homo sapiens Cornulin Proteins 0.000 claims description 12
- 238000012790 confirmation Methods 0.000 claims description 7
- 230000002457 bidirectional effect Effects 0.000 claims description 6
- 239000000284 extract Substances 0.000 claims description 6
- 238000000034 method Methods 0.000 claims description 6
- 238000012549 training Methods 0.000 claims description 6
- 230000003993 interaction Effects 0.000 claims description 4
- 238000012986 modification Methods 0.000 claims description 4
- 230000004048 modification Effects 0.000 claims description 4
- 230000009193 crawling Effects 0.000 claims description 3
- 125000004122 cyclic group Chemical group 0.000 claims description 3
- 238000012217 deletion Methods 0.000 claims description 3
- 230000037430 deletion Effects 0.000 claims description 3
- 238000002372 labelling Methods 0.000 claims description 3
- 238000012805 post-processing Methods 0.000 claims description 3
- 238000013518 transcription Methods 0.000 claims description 3
- 230000035897 transcription Effects 0.000 claims description 3
- 238000000605 extraction Methods 0.000 abstract 1
- 238000005516 engineering process Methods 0.000 description 7
- 238000012423 maintenance Methods 0.000 description 3
- 230000001755 vocal effect Effects 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000001419 dependent effect Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000005192 partition Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 238000012827 research and development Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/20—Education
- G06Q50/205—Education administration or guidance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/951—Indexing; Web crawling techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/10—Office automation; Time management
- G06Q10/103—Workflow collaboration or project management
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/40—Document-oriented image-based pattern recognition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Data Mining & Analysis (AREA)
- Human Resources & Organizations (AREA)
- General Engineering & Computer Science (AREA)
- Tourism & Hospitality (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Educational Administration (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Computing Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Biomedical Technology (AREA)
- Databases & Information Systems (AREA)
- Computational Linguistics (AREA)
- General Business, Economics & Management (AREA)
- Educational Technology (AREA)
- Molecular Biology (AREA)
- Evolutionary Computation (AREA)
- Economics (AREA)
- Biophysics (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- Multimedia (AREA)
- Primary Health Care (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a project management method based on national natural science foundation, which comprises the steps of project increase, uploading of picture attachments of national natural foundation books, automatic identification and extraction of foundation project form information, automatic filling of foundation project information of forms in a system, editing, submission and approval, examination and verification of foundation project information, and inquiry and verification result lookup of WeChat small programs, and can automatically send out messages in a station; the fund project management system comprises a server, an interactive interface, a picture identification module, a project establishment management module and a longitudinal project list module; the fund project information management method and the fund project information management system are simple to operate and easy to maintain; after the operation of the level correction manager is finished, the system can be automatically pushed to the WeChat small program end, and an individual can check the verification result in time, so that the flow time is saved, and the project information verification progress of the applicant and the participators can be informed in time.
Description
Technical Field
The invention relates to a scientific research thesis management method and system based on artificial intelligence, and belongs to the technical field of computer information management.
Background
In many colleges and universities in China, many colleges and universities independently develop new technologies, new products, release patents, papers, generate new achievements and the like, current scientific research activities and scientific research capabilities become important evaluation indexes in talent culture and evaluation of the colleges and universities, and the booster is also used for promoting teachers to improve business levels and teaching quality and social service capabilities. However, most of research and development management work of these scientific research results currently stays in the paper office stage.
With the development of computer software and hardware technology and network technology, computer and network technology has penetrated all corners of society. The internal management of many enterprises and institutions has been networked, which not only increases the management efficiency and saves the management time, but also reduces many unnecessary troubles, and the advantages of the networked management are seen.
In order to strengthen scientific research management vigorously and strengthen scientific research paper control of colleges and universities, fine management is comprehensively implemented to different scientific research modules and runs through various fields of various colleges, paper-free office and informatization of paper management are realized, and the development of a high-efficiency and reasonable scientific research information management system is necessary.
The invention discloses a scientific research management information system of a three-layer higher vocational school based on NET (network application number) in Chinese invention patent with application number 201110079403.6, wherein the system adopts ASP.NET + SQLSever2005 technology, selects B/S mode, and uses C # to realize the functions of system data setting, scientific research result management, scientific research subject management, inquiry, browsing and statistics and system maintenance and management. The system can basically meet the working requirements of scientific research management of some higher vocational schools, and can improve the working efficiency of the higher vocational schools to a certain extent. However, the system is complex in operation, needs teachers to manually input thesis information, and cannot simultaneously meet the requirement of intelligent management of scientific research thesis of colleges and universities.
Disclosure of Invention
Aiming at the problems in the prior art, the invention provides a scientific research thesis management method and system based on artificial intelligence, so that the recording time and labor cost are reduced.
In order to achieve the purpose, the invention adopts the technical scheme that: a scientific research thesis management system based on artificial intelligence comprises a server; the server comprises an artificial intelligent image recognition module, an information input sub-module and an information auditing sub-module; the artificial intelligent image recognition module is used for displaying all, school passing/failing and temporary stored information, displaying an information list in the management module, displaying information and WeChat applet information in the station and displaying a scientific research thesis management state; the information input sub-module is used for displaying input scientific research information, interactively displaying the management state of the scientific research information, and sending an audit WeChat small program message and an in-station message; the information auditing submodule is used for auditing the scientific research information, displaying the auditing state of the scientific research information through an interactive interface, and sending a WeChat small program message and an in-station message.
Further, the information input sub-module and the information auditing sub-module are two of the management modules; the information input sub-module can display the input scientific research information, and after the scientific research information is input through comparison and modification, the information input sub-module enters the information auditing sub-module by clicking 'submission'; if the verification is passed, the application form displayed on the interactive interface is in a school passing state, and simultaneously sending an in-station message and a WeChat applet message to the applicant; if the audit is not passed, the application form displayed by the interactive interface is in a 'school failed' state, and simultaneously sends an in-station message and a WeChat applet message to the applicant.
Further, the management states of the scientific research information displayed through interaction comprise 'all', 'school passed', 'school failed' and 'temporary storage'.
A scientific research thesis management method based on artificial intelligence comprises the following steps;
the method comprises the following steps: the server side automatically crawls the thesis service, runs and crawls the thesis, carries out artificial intelligent picture recognition on the crawled thesis, extracts scientific research thesis information and stores the scientific research thesis information in a recognition result library;
step two: clicking scientific research dynamics-my achievement-all pushing at the client;
step three: the papers automatically pushed by the system can be seen in all the pushing;
step four: and clicking a claim button under the corresponding paper to pop up a claim confirmation interactive page. Clicking to ignore can ignore, but can cancel ignoring;
step five: after confirming that the interactive page selects a series of information such as author sequence, name and the like, clicking to confirm, and then saving the information in the temporary storage;
step six: the scientific research papers can be submitted, edited, deleted and the like in a temporary storage operation column, the examination can be waited for by clicking submission, the clicking editing is to modify the scientific research information automatically filled and input by artificial intelligence, and the clicking deletion is to return the deleted information in the temporary storage to push;
step seven: the auditor automatically compares the submitted scientific research thesis information with the thesis information in the recognition result library to see the modified place, if the auditor passes, the state displayed on all the result list interfaces is 'school pass', the information in the station is sent to the applicant at the same time, meanwhile, the information is pushed from the WeChat small program end, and the scientific research thesis is stored in the school level, the institution level, the individual and participant libraries; if the audit is not passed, the state displayed on the longitudinal item list interface of all the results is 'school failed', and meanwhile, the message in the station is sent to the applicant, and meanwhile, the message is pushed from the WeChat applet end.
Further, the image recognition in the first step is implemented through the crawled scientific research papers, and after the image recognition is implemented through CTPN & CRNN artificial intelligence service, scientific research paper information is automatically recognized and extracted, stored in a recognition result library and pushed to the authors.
Further, the image recognition is based on a model of a CTPN-53+ CRNN network structure and is used for extracting information of scientific research papers and then automatically inputting the information;
CTPN-53, here a CTPN variant, detects the horizontally arranged text information, inputs a picture of the project book:
firstly, extracting features through a Darknet-53 network to obtain a conv5 feature map with the size of 1C H W (C is the number of channels, H is the picture height, and W is the picture width);
then make 3 × 3 sliding windows on conv5, i.e. each point combines the surrounding 3 × 3 region features to obtain a feature vector with length 3 × C; outputting a feature map of 1 × 9C × H × W, which is obviously only the spatial feature learned by CNN;
then feature map is conducted to Reshape: 1 × 9C × H × W → (1 × H) W × 9C
Then, the data stream with N equal to 1, so Batch equal to NH and maximum time length T equal to W is input into the bidirectional LSTM, and the sequence feature of each line is learned; bidirectional LSTM outputs NH × W256, then Reshape restores shape:
NH W256 → N256H W, which contains both spatial and LSTM learned sequence features;
then through the fully connected convolution layer, the characteristic of N512H W is changed, and finally through the RPN network similar to fast R-CNN, text messages are obtained;
CTPN-53 has 3 outputs, text/non-text score, vertical coordinate V ═ Vc，vhAnd left and right horizontal offsets O; the CTPN contains 3 loss functions,
a classification loss function, which distinguishes whether text is present or not by softmax loss,
and
are all regression functions, using L1Calculating a function; the total loss function is as follows:
where 1 and 2 are equal to each other
Then carrying out character recognition on the taken text tokens, and carrying out recognition by using a network architecture of CRNN-53& CTC;
CRNN is divided into three parts: convolutional layer, cyclic network layer, transcription output layer;
the convolutional layer is a common CNN network used for extracting image features, the circulating network layer is a BI-LSTM and aims to continuously extract character sequence features after convolution, and the output layer outputs RNN as softmax and then outputs characters;
the CTC sends the CRNN result obtained above into a CTC algorithm model, wherein the CTC algorithm is a complete end-to-end model training, data do not need to be aligned in advance, and only one input sequence and one output sequence are needed for training; therefore, data alignment and one-to-one labeling are not needed, and CTC directly outputs the probability of sequence prediction without external post-processing; CTC introduces a blank, one spike in the entire piece of text for each predicted class, and other locations that are not spikes are considered blanks. For a piece of text, the final output of the CTC is a sequence of spikes, and does not care how long each word lasts; CTC is by gradient
Adjusting ω -parameter of LSTM to maximize p (l | x); (p (l | x) is the probability of the output l given the input x, ω is the LSTM hidden layer parameter); thereby obtaining the processed text information.
The invention has the beneficial effects that: the scientific research thesis management method and system based on artificial intelligence have the advantages that: the classification management is clear at a glance, and the operation is simple and convenient; the inquiry is convenient through multiple channels; scientific research thesis information is automatically input through an artificial intelligent picture recognition technology and is merged into a library for storage, and the operation flow is simple and easy to learn; after the operation of the applicant or the auditor is finished, the system can automatically remind and automatically send a message to inform the other side, so that the flow time is saved, and the other side can timely inform the audit progress; the scientific research thesis management method and the scientific research thesis management system method based on artificial intelligence can be suitable for information management of teachers in colleges and universities. Teachers, subject managers, academic achievement managers, researchers management departments and the like can all carry out maintenance and management in a grading mode through the system, and various scientific research paper information can be extracted from the library according to different people with different purposes.
Drawings
FIG. 1 is a flow chart of a scientific research thesis management method and system method based on artificial intelligence of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is further described in detail below with reference to the accompanying drawings and examples. It should be understood, however, that the description herein of specific embodiments is only intended to illustrate the invention and not to limit the scope of the invention.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs, and the terms used herein in the specification of the present invention are for the purpose of describing particular embodiments only and are not intended to limit the present invention.
As shown in fig. 1, a scientific research thesis management system based on artificial intelligence comprises a server; the server comprises an artificial intelligent image recognition module, an information input sub-module and an information auditing sub-module; the artificial intelligent image recognition module is used for displaying all, school passing/failing and temporary stored information, displaying an information list in the management module, displaying information and WeChat applet information in the station and displaying a scientific research thesis management state; the information input sub-module is used for displaying input scientific research information, interactively displaying the management state of the scientific research information, and sending an audit WeChat small program message and an in-station message; the information auditing submodule is used for auditing the scientific research information, displaying the auditing state of the scientific research information through an interactive interface, and sending a WeChat small program message and an in-station message.
Preferably, in this embodiment, the information entry sub-module and the information audit sub-module are two of the management modules; the information input sub-module can display the input scientific research information, and after the scientific research information is input through comparison and modification, the information input sub-module enters the information auditing sub-module by clicking 'submission'; if the verification is passed, the application form displayed on the interactive interface is in a school passing state, and simultaneously sending an in-station message and a WeChat applet message to the applicant; if the audit is not passed, the application form displayed by the interactive interface is in a 'school failed' state, and simultaneously sends an in-station message and a WeChat applet message to the applicant.
Preferably, the management states of the scientific research information displayed through interaction include "all", "school passed", "school failed", and "temporary storage".
A scientific research thesis management method based on artificial intelligence comprises the following steps;
the method comprises the following steps: the server side automatically crawls the thesis service, runs and crawls the thesis, carries out artificial intelligent picture recognition on the crawled thesis, extracts scientific research thesis information and stores the scientific research thesis information in a recognition result library;
step two: clicking scientific research dynamics-my achievement-all pushing at the client;
step three: the papers automatically pushed by the system can be seen in all the pushing;
step four: and clicking a claim button under the corresponding paper to pop up a claim confirmation interactive page. Clicking to ignore can ignore, but can cancel ignoring;
step five: after confirming that the interactive page selects a series of information such as author sequence, name and the like, clicking to confirm, and then saving the information in the temporary storage;
step six: the scientific research papers can be submitted, edited, deleted and the like in a temporary storage operation column, the examination can be waited for by clicking submission, the clicking editing is to modify the scientific research information automatically filled and input by artificial intelligence, and the clicking deletion is to return the deleted information in the temporary storage to push;
step seven: the auditor automatically compares the submitted scientific research thesis information with the thesis information in the recognition result library to see the modified place, if the auditor passes, the state displayed on all the result list interfaces is 'school pass', the information in the station is sent to the applicant at the same time, meanwhile, the information is pushed from the WeChat small program end, and the scientific research thesis is stored in the school level, the institution level, the individual and participant libraries; if the audit is not passed, the state displayed on the longitudinal item list interface of all the results is 'school failed', and meanwhile, the message in the station is sent to the applicant, and meanwhile, the message is pushed from the WeChat applet end.
Preferably, in the image recognition of the first step, after the crawled scientific research papers are subjected to CTPN & CRNN artificial intelligence service, scientific research paper information is automatically recognized and extracted, stored in a recognition result library, and pushed to the author.
Preferably, in the embodiment, the image recognition is based on a model of a CTPN-53+ CRNN network structure, and is used for extracting information of scientific research papers and then automatically inputting the information;
CTPN-53, here a CTPN variant, detects the horizontally arranged text information, inputs a picture of the project book:
firstly, extracting features through a Darknet-53 network to obtain a conv5 feature map with the size of 1C H W (C is the number of channels, H is the picture height, and W is the picture width);
then make 3 × 3 sliding windows on conv5, i.e. each point combines the surrounding 3 × 3 region features to obtain a feature vector with length 3 × C; outputting a feature map of 1 × 9C × H × W, which is obviously only the spatial feature learned by CNN;
then feature map is conducted to Reshape: 1 × 9C × H × W → (1 × H) W × 9C
Then, the data stream with N equal to 1, so Batch equal to NH and maximum time length T equal to W is input into the bidirectional LSTM, and the sequence feature of each line is learned; bidirectional LSTM outputs NH × W256, then Reshape restores shape:
NH W256 → N256H W, which contains both spatial and LSTM learned sequence features;
then through the fully connected convolution layer, the characteristic of N512H W is changed, and finally through the RPN network similar to fast R-CNN, text messages are obtained;
CTPN-53 has 3 outputs, text/non-text score, vertical coordinate V ═ Vc，vhAnd left and right horizontal offsets O; the CTPN contains 3 loss functions,
a classification loss function, which distinguishes whether text is present or not by softmax loss,
and
are all regression functions, using L1Calculating a function; the total loss function is as follows:
where 1 and 2 are equal to each other
Then carrying out character recognition on the taken text tokens, and carrying out recognition by using a network architecture of CRNN-53& CTC;
CRNN is divided into three parts: convolutional layer, cyclic network layer, transcription output layer;
the convolutional layer is a common CNN network used for extracting image features, the circulating network layer is a BI-LSTM and aims to continuously extract character sequence features after convolution, and the output layer outputs RNN as softmax and then outputs characters;
the CTC sends the CRNN result obtained above into a CTC algorithm model, wherein the CTC algorithm is a complete end-to-end model training, data do not need to be aligned in advance, and only one input sequence and one output sequence are needed for training; therefore, data alignment and one-to-one labeling are not needed, and CTC directly outputs the probability of sequence prediction without external post-processing; CTC introduces a blank, one spike in the entire piece of text for each predicted class, and other locations that are not spikes are considered blanks. For a piece of text, the final output of the CTC is a sequence of spikes, and does not care how long each word lasts; CTC is by gradient
Adjusting ω -parameter of LSTM to maximize p (l | x); (p (l | x) is the probability of the output l given the input x, ω is the LSTM hidden layer parameter); thereby obtaining the processed text information.
My results module may display all results information, including "school passed", "school failed", and "staged". My results module may also display all pushes, categorized by year and paper source. In "staging," the paper may be subjected to "commit," "edit," and "delete" operations. And after the 'submission' is clicked, a final confirmation information interaction interface is popped up, and if the confirmation is clicked, the submission is successful and the audit is waited. After clicking on 'edit', the automatically entered thesis information can be directly modified. After clicking on "delete", the paper information in "scratch" can be deleted and redisplayed in a push.
The information auditing submodule provides auditing and editing operation functions in the 'thesis' submodule for an auditor to operate. The scientific research information needing to be input in the scientific research thesis information management module comprises basic information, author information, evidence materials and dependent projects. After scientific research information is input, the added information can be inquired in the scientific research information management module according to retrieval conditions such as a thesis name, a affiliated department, an author name, a publication grade, a thesis type, a publication date, a publication name, a listing category, a sci partition and the like. The basic information recorded in the scientific research thesis information management module comprises: subject of thesis, publication/publication date, publication/collection name, type of thesis, department affiliated, category of listing, publication level, DOI, PDF full text, first level subject, publication scope, volume/date/page, SCI thesis partition, impact factor, school signature, ISSN, CN number, submission date, proof of search.
The author information input in the scientific research thesis information management module comprises: work order number, author type, author name, academic calendar, job title, role type, work department, and operation. The evidence-based materials input in the scientific research thesis information management module comprise: sequence number, document type, file name. The supporting projects recorded in the scientific research thesis information management module comprise: person in charge, project status, winning selection. As may be skipped without a dependent item. The reprinting condition recorded in the scientific research thesis information management module comprises the following steps: a reprint name, a reprint time, a reprint type, and an operation. And may be skipped if there is no transfer.
The invention has the beneficial effects that: the scientific research thesis management method and system based on artificial intelligence have the advantages that: the classification management is clear at a glance, and the operation is simple and convenient; the inquiry is convenient through multiple channels; scientific research thesis information is automatically input through an artificial intelligent picture recognition technology and is merged into a library for storage, and the operation flow is simple and easy to learn; after the operation of the applicant or the auditor is finished, the system can automatically remind and automatically send a message to inform the other side, so that the flow time is saved, and the other side can timely inform the audit progress; the scientific research thesis management method and the scientific research thesis management system method based on artificial intelligence can be suitable for information management of teachers in colleges and universities. Teachers, subject managers, academic achievement managers, researchers management departments and the like can all carry out maintenance and management in a grading mode through the system, and various scientific research paper information can be extracted from the library according to different people with different purposes.
Firstly, at a server side, after an automatic crawling thesis service runs a crawling thesis, an administrator pushes scientific research thesis information to all users. The user can click on the scientific research dynamics-the result-all the pushed information at the client, the paper automatically pushed by the system can be seen in the pushed information, and the user can pop up the claim confirmation interactive page by clicking on the claim button under the corresponding paper. Clicking to ignore can ignore. And automatically carrying out artificial intelligent picture recognition on the claimed paper in the popped up claimed confirmation interactive page, extracting scientific research paper information, then automatically filling the scientific research paper information into the current interactive page, and storing the scientific research paper information into a recognition result library, wherein a user can edit, modify and store the filled scientific research information. The user can submit the application after confirming the correctness, and the user can go through the hospital and school audit step by step or can directly carry out the school grade audit. The yard and school grade auditing is to automatically compare the submitted application information with the information previously input into the identification library and check the places modified by the user, if the verification is reasonable, the verification is passed, otherwise, the verification is not passed. If the courtyard fails, the station sends the message in the station and simultaneously pushes the message from the WeChat applet end. The application is then returned and the user can modify it again. And the user can directly send to the school level for auditing when the academy level does not pass. And after the final school grade audit is passed, automatically storing the scientific research paper information into a school grade library, a hospital grade library and a personal and participant library, sending an internal message to an applicant, and simultaneously pushing the internal message from a WeChat small program terminal.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents or improvements made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (6)
1. A scientific research thesis management system based on artificial intelligence is characterized by comprising a server; the server comprises an artificial intelligent image recognition module, an information input sub-module and an information auditing sub-module; the artificial intelligent image recognition module is used for displaying all, school passing/failing and temporary stored information, displaying an information list in the management module, displaying information and WeChat applet information in the station and displaying a scientific research thesis management state; the information input sub-module is used for displaying input scientific research information, interactively displaying the management state of the scientific research information, and sending an audit WeChat small program message and an in-station message; the information auditing submodule is used for auditing the scientific research information, displaying the auditing state of the scientific research information through an interactive interface, and sending a WeChat small program message and an in-station message.
2. The scientific research thesis management system based on artificial intelligence of claim 1, further comprising a management module, wherein the information entry sub-module and the information audit sub-module are two of the management module; the information input sub-module can display the input scientific research information, and after the scientific research information is input through comparison and modification, the information input sub-module enters the information auditing sub-module by clicking 'submission'; if the verification is passed, the application form displayed on the interactive interface is in a school passing state, and simultaneously sending an in-station message and a WeChat applet message to the applicant; if the audit is not passed, the application form displayed by the interactive interface is in a 'school failed' state, and simultaneously sends an in-station message and a WeChat applet message to the applicant.
3. The system of claim 1, wherein the management states of scientific research information displayed by interaction include "all", "school passed", "school not passed" and "temporary storage".
4. A scientific research thesis management method based on artificial intelligence is characterized by comprising the following steps;
the method comprises the following steps: the server side automatically crawls the thesis service, runs and crawls the thesis, carries out artificial intelligent picture recognition on the crawled thesis, extracts scientific research thesis information and stores the scientific research thesis information in a recognition result library;
step two: clicking scientific research dynamics-my achievement-all pushing at the client;
step three: the papers automatically pushed by the system can be seen in all the pushing;
step four: and clicking a claim button under the corresponding paper to pop up a claim confirmation interactive page. Clicking to ignore can ignore, but can cancel ignoring;
step five: after confirming that the interactive page selects a series of information such as author sequence, name and the like, clicking to confirm, and then saving the information in the temporary storage;
step six: the scientific research papers can be submitted, edited, deleted and the like in a temporary storage operation column, the examination can be waited for by clicking submission, the clicking editing is to modify the scientific research information automatically filled and input by artificial intelligence, and the clicking deletion is to return the deleted information in the temporary storage to push;
step seven: the auditor automatically compares the submitted scientific research thesis information with the thesis information in the recognition result library to see the modified place, if the auditor passes, the state displayed on all the result list interfaces is 'school pass', the information in the station is sent to the applicant at the same time, meanwhile, the information is pushed from the WeChat small program end, and the scientific research thesis is stored in the school level, the institution level, the individual and participant libraries; if the audit is not passed, the state displayed on the longitudinal item list interface of all the results is 'school failed', and meanwhile, the message in the station is sent to the applicant, and meanwhile, the message is pushed from the WeChat applet end.
5. The scientific research thesis management method based on artificial intelligence as claimed in claim 4, wherein the image recognition in the first step is implemented by crawling scientific research thesis, and after being subjected to CTPN & CRNN artificial intelligence service, scientific research thesis information is automatically recognized and extracted, stored in a recognition result library, and pushed to a writer.
6. The scientific research thesis management method based on artificial intelligence as claimed in claims 4 and 5, wherein the image recognition is based on a model of CTPN-53+ CRNN network structure for extracting information of scientific research thesis and then automatically entering;
CTPN-53, here a CTPN variant, detects the horizontally arranged text information, inputs a picture of the project book:
firstly, extracting features through a Darknet-53 network to obtain a conv5 feature map with the size of 1C H W (C is the number of channels, H is the picture height, and W is the picture width);
then make 3 × 3 sliding windows on conv5, i.e. each point combines the surrounding 3 × 3 region features to obtain a feature vector with length 3 × C; outputting a feature map of 1 × 9C × H × W, which is obviously only the spatial feature learned by CNN;
then feature map is conducted to Reshape: 1 × 9C × H × W → (1 × H) W × 9C
Then, the data stream with N equal to 1, so Batch equal to NH and maximum time length T equal to W is input into the bidirectional LSTM, and the sequence feature of each line is learned; bidirectional LSTM outputs NH × W256, then Reshape restores shape: NH W256 → N256H W, which contains both spatial and LSTM learned sequence features;
then through the fully connected convolution layer, the characteristic of N512H W is changed, and finally through the RPN network similar to fast R-CNN, text messages are obtained;
CTPN-53 has 3 outputs, text/non-text score, vertical coordinate V ═ VG，vkAnd left and right horizontal offsets O; the CTPN contains 3 loss functions,
classification loss function, in sThe soft max loss distinguishes whether it is text or not,
and
are all regression functions, using L1Calculating a function; the total loss function is as follows:
where 1 and 2 are equal to each other
Then carrying out character recognition on the taken text tokens, and carrying out recognition by using a network architecture of CRNN-53& CTC;
CRNN is divided into three parts: convolutional layer, cyclic network layer, transcription output layer;
the convolutional layer is a common CNN network used for extracting image features, the circulating network layer is a BI-LSTM and aims to continuously extract character sequence features after convolution, and the output layer outputs RNN as softmax and then outputs characters;
the CTC sends the CRNN result obtained above into a CTC algorithm model, wherein the CTC algorithm is a complete end-to-end model training, data do not need to be aligned in advance, and only one input sequence and one output sequence are needed for training; therefore, data alignment and one-to-one labeling are not needed, and CTC directly outputs the probability of sequence prediction without external post-processing; CTC introduces a blank, one spike in the entire piece of text for each predicted class, and other locations that are not spikes are considered blanks. For a piece of text, the final output of the CTC is a sequence of spikes, and does not care how long each word lasts; CTC is by gradient
Adjusting ω -parameter of LSTM to maximize p (l | x); (p (l | x) is the probability of outputting l, ω, given an input xIs LSTM hidden layer parameter); thereby obtaining the processed text information.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110581579.5A CN113160016A (en) | 2021-05-27 | 2021-05-27 | Scientific research thesis management method and system based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110581579.5A CN113160016A (en) | 2021-05-27 | 2021-05-27 | Scientific research thesis management method and system based on artificial intelligence |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113160016A true CN113160016A (en) | 2021-07-23 |
Family
ID=76877714
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110581579.5A Pending CN113160016A (en) | 2021-05-27 | 2021-05-27 | Scientific research thesis management method and system based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113160016A (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108197258A (en) * | 2017-12-29 | 2018-06-22 | 北京农业信息技术研究中心 | A kind of Science Research Information Management System and science research information management method |
| CN112330303A (en) * | 2020-11-27 | 2021-02-05 | 同济大学建筑设计研究院(集团)有限公司 | Intelligent project evaluation cooperative management system |
-
2021
- 2021-05-27 CN CN202110581579.5A patent/CN113160016A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108197258A (en) * | 2017-12-29 | 2018-06-22 | 北京农业信息技术研究中心 | A kind of Science Research Information Management System and science research information management method |
| CN112330303A (en) * | 2020-11-27 | 2021-02-05 | 同济大学建筑设计研究院(集团)有限公司 | Intelligent project evaluation cooperative management system |
Non-Patent Citations (3)
| Title |
|---|
| BESTRIVEM: "CTPN详解", 《CSDN博客》 * |
| YOUBIKA: "论文网推数据认领流程工作手册（含注意事项）", 《原创力文档》 * |
| 网络: "一文读懂CRNN+CTC文字识别", 《ICODE9》 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US6098047A (en) | Constructing method of organization activity database, analysis sheet used therein, and organization activity management system | |
| AU758232B2 (en) | Single-document active user interface, method and system for implementing same | |
| Abdulwahid et al. | Library Management System Using Artificial Intelligence | |
| Wang et al. | Strategic development trend and key factors analysis of Airport City in Taiwan | |
| CN113627797B (en) | Method, device, computer equipment and storage medium for generating staff member portrait | |
| JP7373091B1 (en) | Information processing system, information processing method and program | |
| CN111710428B (en) | Biomedical text representation method for modeling global and local context interaction | |
| CN111274779A (en) | Legal document generation system and method based on user experience prediction | |
| CN113449957A (en) | Intelligent working system based on PAGEOFFLICE control | |
| CN113160016A (en) | Scientific research thesis management method and system based on artificial intelligence | |
| CN113643161A (en) | Project management method and system based on national natural science foundation project | |
| CN116994467A (en) | Answer area acquisition and electronic job processing method, system, equipment and medium | |
| CN113111920B (en) | Project data management system based on PLM and application method | |
| CN109165323A (en) | A kind of family's information intelligent processing system | |
| Tyshchenko et al. | Electronic System" All-Ukrainian Toloka Archival Card Index": Structure, Tools, Prospects of Development. | |
| Baker | ‘Providing a layman’s guide to the scheme’: museum computing, professional personas and documentary labour in the United Kingdom, 1967-1983 | |
| Yang | Visualization Analysis of English Think Tank Data Based on Genetic Algorithm | |
| Gasser | Research partnerships, user participation, extended outreach–some of ETH Library's steps beyond digitisation | |
| Peneti et al. | Text Recognition Based On Encoder And Decoder Framework | |
| Liang et al. | Exploration and Practice of Integrated Indoor and Outdoor Construction of Experimental Animal Center. | |
| Minggao et al. | Research on the Application of LLM in Power Finance Middle Platform | |
| Sroka et al. | “The Dwindling Legacy that Is Food for Mice and Flames”: Discovery and Preservation of Illinois Historic Newspapers through the Illinois Digital Newspaper Project, 2009–2015 | |
| Cohen | Field Notes: An Exploration of Crowdsourcing Platforms for Natural History Collections | |
| Avny | The necessity of change–how the fourth industrial revolution urges the entrepreneurs to alter their leadership attributes | |
| Prentice | The environmental scan |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210723 |
|
| RJ01 | Rejection of invention patent application after publication |